A connection between an AI coding agent and Twenty, a customer-relationship management system for tracking people, companies, sales opportunities, tasks, and notes.

Use it to search, filter, count, create, update, or delete data in a self-hosted or cloud Twenty account.

It lets the agent work with CRM records without requiring separate manual data entry or searches.

twenty-crm — Skill for Claude Code and Codex by nobilix

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add nobilix/twenty-crm-skill --skill twenty-crm

Clone the repo

git clone --depth 1 https://github.com/nobilix/twenty-crm-skill

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin twenty-crm — /plugin install twenty-crm after adding the marketplace above.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nobilix/twenty-crm-skill/twenty-crm/github.svg)](https://agentmods.dev/skills/nobilix/twenty-crm-skill/twenty-crm)

Your own site

<a href="https://agentmods.dev/skills/nobilix/twenty-crm-skill/twenty-crm"><img src="https://agentmods.dev/badge/skills/nobilix/twenty-crm-skill/twenty-crm/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nobilix/twenty-crm-skill/twenty-crm"><img src="https://agentmods.dev/badge/skills/nobilix/twenty-crm-skill/twenty-crm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,781 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00148	$0.02781
Opus 5.5	$0.00059	$0.01112
Sonnet 5.5	$0.00030	$0.00556
Haiku 4.5	$0.00015	$0.00278

Measured 2mo ago against content hash 10fd9d72d1e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

twenty-crm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/twenty.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/twenty-crm/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Twenty CRM

Reusable across any Twenty deployment. The skill drives ocli — a CLI generated from your workspace's OpenAPI spec. Per-instance state is an ocli profile under ~/.ocli/; the skill keeps only a one-line pointer in ~/.config/twenty-cli/config.json. Nothing is hardcoded.

Step 0: preflight (always)

node scripts/twenty.mjs preflight

STATUS=ready → proceed. Output also gives PROFILE=<name> (the ocli profile, usually twenty), URL=<base-url> (use it to build UI links), and METADATA=<name> if the metadata profile was set up.
non-zero exit → not configured. Stderr prints the two things setup needs (URL, API key) and the two setup paths below; pick by context. For the full walkthrough load references/setup-guide.md.

not_ready is not sticky. Setup happens in the user's own terminal, so a config that didn't exist this turn may exist the next. If you reported not_ready and the user comes back with any CRM request, re-run preflight first — don't repeat the "not configured" message from memory.

Setup

Idempotent — re-running updates the existing profile. New here? references/setup-guide.md has the full step-by-step (where the URL comes from, how to create the API key).

You need: the URL you open Twenty at — self-hosted https://crm.your-company.com or cloud https://your-workspace.twenty.com (the workspace subdomain, not api.twenty.com — that host has no UI, so record links break); setup appends /rest. Plus an API key from Settings → APIs & Webhooks → + Create key.

Recommend the user run setup in their own terminal — the API key is typed as hidden input, so it never lands in the chat transcript. Tell them why, and give them:

node <skill-path>/scripts/twenty.mjs setup

That's the safe default. Only if the user themselves puts the URL + key in chat (or explicitly asks you to run it) use the non-interactive form:

node <skill-path>/scripts/twenty.mjs setup --non-interactive --url <url> --token <key>

Read the full file on GitHub · 184 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 184 lines · 148 tokens per session scan A 10fd9d72d1e2

Subscribe to this mod's changes

twenty-crm is a skill published in the GitHub repository nobilix/twenty-crm-skill (15 stars, last pushed 5mo ago), licensed MIT. It adds 148 tokens to every session and 2,781 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code agent-skills codex crm restish skills

twenty-crm next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
twenty-crmnobilix/twenty-crm-skill	Skill	15	5mo ago	MIT	A	148	Claude Code, Codex
claude-md-improveranthropics/claude-plugins-official	Skill	47k	today	Apache-2.0	A	82	Claude Code
agent-platform-model-registrygoogle/skills	Skill	24k	today	Apache-2.0	A	60	Claude Code, Codex
gke-reliabilitygoogle/skills	Skill	24k	today	Apache-2.0	A	85	Claude Code, Codex
gke-workload-securitygoogle/skills	Skill	24k	today	Apache-2.0	A	171	Claude Code, Codex
google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skills	Skill	24k	today	Apache-2.0	A	132	Claude Code, Codex
glance-canonical-layoutsandroid/skills	Skill	10k	2d ago	Apache-2.0	A	56	Claude Code